AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Decision Tree for Locally Private Estimation with Public Data

Yuheng Ma, Han Zhang, Yuchao Cai, Hanfang Yang

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 500 public samples while using fewer private samples (7,000 vs 8,000) (ablation)LPDT · Synthetic sin(16X), eps=8MSE: 1.19 -> 1.08Improved
increase tree depth s from small to large (ablation)LPDT · Synthetic, eps in {3,4,6,8}MSEMixed
increase privacy budget epsLPDT · Synthetic, optimal depth sMSEImproved
vary minimum leaf size nl from 15 to 135 (ablation)LPDT · Synthetic, eps in {3,4,6,8}MSE: nl = 125 best at eps = 3Mixed
increase eps from 0.5 to 10LPDT vs PHIST/APHIST/DECONV · SyntheticMSEImproved
use LPDT instead of PHIST, APHIST and DECONVLPDT-M / LPDT-V · 12 real datasets, eps=2,6MSEImproved
replace max-edge rule with CART variance reduction rule (LPDT-V vs LPDT-M) (ablation)LPDT · Real datasets, eps=6MSE: CPU 3.02e+2 -> 6.15e+1; FIS 1.65e+0 -> 1.76e+0Mixed
train decision tree on public data only (n_q = 0.1n) vs LPDT (ablation)LPDT · Real datasets, eps=6MSEImproved
add 100 public samples to LPDT with DP vs non-private PHISTLPDT · Red wineMSE: 1,100 samples vs 660 samples for same MSEImproved
use LPDT with public data from different distribution vs DT on public data aloneLPDT-M · Chicago taxiMSE: 3.71 -> 2.86Improved
use LPDT eps=2 vs histogram baselines at eps=8LPDT-M · Chicago taxiMSE: 4.89 vs 17.22Improved
increase portion of public data delta in partition data from 0.1 to 0.9 (ablation)LPDT · Wine and Chicago taxiMSEHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy